Native multimodal GLM model for efficient coding and long-horizon agent tasks

Details

FieldValue
idglm-5-3-flash
familyglm-flash
modalitytext+image+video+pdf->text
context_length1000000
max_output_tokens131072
release_date2026-08-26
is_open_weightsyes
supports_tool_callyes
supports_reasoningyes
supports_structured_outputyes
supports_attachmentyes
input_modalitiestext, image, video, pdf
output_modalitiestext